I get excited when I hear about major new R&D, backed by major investment, all for a major goal. Like this one: IBM’s long-term goal to build a neurosynaptic system with ten billion neurons and a hundred trillion synapses, all while consuming only one kilowatt of power and occupying less than two liters of volume.
As a step toward that goal, IBM is committing $3 billion over the next 5 years for R&D to push the limits of chip technology. Cloud computing and big-data systems pose new demands like bandwidth-to-memory, high-speed communication and power consumption, which in turn demand more horsepower. IBM wants to breed the ultimate thoroughbred. So it’s using the $3 billion spend to push the limits of chip technology to smaller and more powerful scales. The R&D teams will include IBM research scientists from Albany and Yorktown, N.Y., Almaden, Calif. and Europe.
What’s really interesting is the semiconductor threshold: IBM says it wants to use the $3 billion to pave the way toward the 7 nanometer plateau (10,000 times thinner than a strand of human hair). IBM researchers and other semiconductor experts predict that while challenging, semiconductors show promise to scale from today’s 22-nanometer standard down to 14 and then 10 nanometers in the next several years. However, scaling to 7 nanometers (and perhaps below) by the end of the decade will require significant investment and innovation in semiconductor architectures as well as invention of new tools and techniques for manufacturing.
What happens beyond 7 nanometers? Then it’s time to ditch silicon and move to potential alternatives like carbon nanotubes or non-traditional computational approaches such as neuromorphic computing, cognitive computing, machine-learning techniques and quantum computing. So the quicker we get to 7 nanometers, the quicker we break into the promise of, say, quantum computing. And the quicker we break into the next computing revolution, the quicker we reach defining milestones of human history like interstellar travel and the end of disease. I firmly believe that.